LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Hermes 3 Llama 3.1 8B Bnb 4bit by unsloth

 »  All LLMs  »  unsloth  »  Hermes 3 Llama 3.1 8B Bnb 4bit   URL Share it on

  1504   

Hermes 3 Llama 3.1 8B Bnb 4bit is an open-source language model by unsloth. Features: 8b LLM, VRAM: 5.7GB, Context: 128K, License: llama3.1, Quantized, LLM Explorer Score: 0.17.

  Arxiv:2408.11857   4-bit   4bit Base model:nousresearch/hermes... Base model:quantized:nousresea...   Bitsandbytes   Conversational   Deploy:azure   En   Endpoints compatible   Facebook   Llama   Llama-3   Meta   Quantized   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Hermes-3-Llama-3.1-8B-bnb-4bit 

Hermes 3 Llama 3.1 8B Bnb 4bit Benchmarks

LLME Score: 0.17228
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Hermes 3 Llama 3.1 8B Bnb 4bit (unsloth/Hermes-3-Llama-3.1-8B-bnb-4bit)
🌟 Advertise your project 🚀

Hermes 3 Llama 3.1 8B Bnb 4bit Parameters and Internals

Model Type 
Generalist Language Model
Additional Notes 
Quantized with NeuralMagic's FP8 for optimized use on VLLM inference engine
Supported Languages 
en (Native)
Training Details 
Methodology:
Full parameter finetune of the Llama-3.1 405B foundation model
Hardware Used:
LambdaLabs 1-Click Cluster
Model Architecture:
Based on Llama-3.1 405B with an expanded set of capabilities building on Hermes 2
Input Output 
Input Format:
ChatML for structured dialogues, compatible with OpenAI endpoints
Accepted Modalities:
text
Output Format:
Natural language response or structured JSON
Release Notes 
Version:
3
Date:
2024
Notes:
Latest flagship model in the Hermes series of LLMs
LLM NameHermes 3 Llama 3.1 8B Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/Hermes-3-Llama-3.1-8B-bnb-4bit 
Base Model(s)  NousResearch/Hermes-3-Llama-3.1-8B   NousResearch/Hermes-3-Llama-3.1-8B
Model Size8b
Required VRAM5.7 GB
Updated2026-04-10
Maintainerunsloth
Model Typellama
Model Files  5.7 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licensellama3.1
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Hermes 3 Llama 3.1 8B Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB162
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB91
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB32
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB60
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB52925
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB30717
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB63
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB01
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB161
...B Instruct 262k V2 EXL2 6.0bpw256K / 6.7 GB41

Rank the Hermes 3 Llama 3.1 8B Bnb 4bit Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer